chembert-lower-lower-cased-chemrxn-ner
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6958
- Precision: 0.4850
- Recall: 0.5249
- F1: 0.5042
- Accuracy: 0.7883
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 51 | 0.9392 | 0.3143 | 0.2072 | 0.2498 | 0.7233 |
No log | 2.0 | 102 | 0.8605 | 0.5862 | 0.1596 | 0.2509 | 0.7460 |
No log | 3.0 | 153 | 0.7388 | 0.4787 | 0.3495 | 0.4040 | 0.7742 |
No log | 4.0 | 204 | 0.7017 | 0.4779 | 0.4065 | 0.4393 | 0.7788 |
No log | 5.0 | 255 | 0.7255 | 0.5238 | 0.4217 | 0.4672 | 0.7877 |
No log | 6.0 | 306 | 0.6908 | 0.4837 | 0.5249 | 0.5035 | 0.7848 |
No log | 7.0 | 357 | 0.6958 | 0.4850 | 0.5249 | 0.5042 | 0.7883 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 0